Sign in

Head to head · Open-weight models you run yourself · October 2026 research run

North Mini Code 1.0 vs Qwen3.5-0.8B

North Mini Code 1.0 scores 61 (C) on agent readiness against Qwen3.5-0.8B's 46.7 (D), and leads in 3 of 4 scored categories. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons

North Mini Code 1.0Cohere · Open-weight model C61/100#80 of 160 open-weight models Qwen3.5-0.8BAlibaba (Qwen team) · Open-weight model D46.7/100#156 of 160 open-weight models

Which one, for what

North Mini Code 1.0 C

Best for Developers who want a coding agent on their own GPU with a permissive licence

Ahead on

  • Reach, 85 against 80
  • Risk, 60 against 55
  • Agent interface, 85 against 60

Watch for

No limitations, safety results, languages or data description on the card

Qwen3.5-0.8B D

Best for Builders who want a near-free local helper or fine-tuning base for narrow tasks on a phone-class device, laptop or CPU

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No quantised build from Alibaba and no inference provider found

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Agent interface North Mini Code 1.0 +25

North Mini Code 1.0 85

Chat template 20, chat_template.jinja in the repository (12,397 characters). Tool-calling format 25, the card documents how tools are declared (JSON schema through the chat template), how the call and its thinking go back into the history and how results are appended, and names the cohere_command4 tool-call parser for vLLM, which released vLLM has. Trained tool calling 20, the card says the model was specifically trained with tool-use capabilities for agentic coding, with reinforcement learning on verifiable tasks, and the template renders every call in a turn with thinking between them. Structured output 0, JSON schema is for describing tools. Reasoning control 10, the template has a reasoning_effort setting, and the card names the cohere_command4 reasoning parser, which returns thinking apart from the answer. Context 10, 256K tokens per the card, with 64K of output, and 500,000 positions in config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.

Qwen3.5-0.8B 60

The template ships in the repository (20) and the model was trained for tool use with several calls per turn in the template (20). Tool-calling format gets 10, because the card names the qwen3_coder parser but leaves the format to the template. Reasoning control scores 0, since the card shows how to turn thinking on but not where the reasoning comes back. 262,144 tokens is native (10). Structured output scores 0, as nothing documents JSON output for the model. 20+10+20+0+0+10 = 60.

Reach North Mini Code 1.0 +5

North Mini Code 1.0 85

Memory 25, the smallest build from Cohere is the w4a16 repository, 19.38 GB, and 19.38 GB × 1.2 = 23.3 GB, within 24 GB. Unsloth's GGUF isn't read for this line. Runtimes 20, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the cohere2_moe model, and llama.cpp b12242 has the cohere2moe architecture. Builds 15, Quantised builds from Cohere at two precisions, FP8 and 4-bit weights (w4a16), each in its own repository. Terms 15, Apache 2.0 in the metadata and on the card, an OSI licence with nothing added. Download 10, the Hub API reports gated false for the model and its builds on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 25 + 20 + 15 + 15 + 10 + 0 = 85.

Qwen3.5-0.8B 80

Memory earns the full 30, since LM Studio's Q4_K_M build with its projector is 0.73 GB (0.88 GB with the fifth added) and Ollama's Q8_0 build was 1.0 GB, both far within 16 GB. Alibaba publishes no quantised 0.8B, so builds scores 0. Runtimes reach the 25 cap on llama.cpp, Ollama (through its pinned llama.cpp), vLLM, SGLang, LM Studio and Transformers. Apache 2.0 with nothing added gives terms 15 and the ungated repository download 10. Hosted too scores 0, as the Hub maps no inference provider to this size. 30+25+0+15+10+0 = 80.

Risk North Mini Code 1.0 +5

North Mini Code 1.0 60

File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in Cohere's verified CohereLabs organisation, which cohere.com links to per our other Cohere listings (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 5, Cohere's trust centre holds a responsible disclosure policy with a bug bounty, as recorded on our Cohere listings (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.

Qwen3.5-0.8B 55

Safetensors only with no remote code gives file safety its 25, and files in the Qwen organisation the publisher's GitHub links to, each with a hash on the Hub, give provenance 15. The Apache 2.0 licence carries none of the deductions, so licence risk keeps 15. Safety evaluation, agent guidance and a security programme score 0, since the card has no safety results or agent cautions and no reporting route was found. The Qwen3.5 blog and Alibaba's security response centre couldn't be read, so those are scored as absent and left open. 25+15+0+0+15+0 = 55.

Score by category

CategoryWeight this runNorth Mini Code 1.0Qwen3.5-0.8BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258580North Mini Code 1.0 +5
Risk20%206055North Mini Code 1.0 +5
Agent interface10%108560North Mini Code 1.0 +25
Documentation and upkeep10%103637Qwen3.5-0.8B +1
Negative events≤1500
TotalC 61/100D 46.7/100

Facts side by side

FactNorth Mini Code 1.0Qwen3.5-0.8B
KindOpen-weight modelOpen-weight model
VendorCohereAlibaba (Qwen team)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-07-292026-03-02
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.8/5 (4)

Verdicts

North Mini Code 1.0

A coding agent model that fits one 24 GB GPU at 4 bits, trained for tool use, with a 256K context, Apache 2.0 and four released runtimes. It's a research release and reads like one: nothing on limitations, safety or data, the card's run instructions are out of date, and Cohere hasn't answered a question on the repository.

Qwen3.5-0.8B

A tiny vision-language model for prototypes, fine-tuning and narrow local steps such as routing, tagging or reading an image. It runs in about 1 GB at 4 or 8 bits in six runtimes under plain Apache 2.0. Keep thinking off, since the card warns it loops. The card has no safety results, and Qwen has answered none of its discussions.

Before you call either

North Mini Code 1.0

  1. Serve it with vLLM 0.33.0 or later and --tool-call-parser cohere_command4 --reasoning-parser cohere_command4 --enable-auto-tool-choice, with cohere_melody installed
  2. Pass the model's thinking back with its tool calls on every turn. The card says results drop without it
  3. Describe tools in JSON schema and append tool results as a dictionary with the tool role
  4. Use temperature 1.0 and top_p 0.95
  5. For llama.cpp the GGUF files are Unsloth's or bartowski's conversions, not Cohere's
  6. It's text only. Don't send images

Qwen3.5-0.8B

  1. Smallest start is ollama run qwen3.5:0.8b, or qwen3.5:0.8b-q8_0 at 1.0 GB
  2. Full precision vllm serve Qwen/Qwen3.5-0.8B --port 8000 --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser qwen3_coder
  3. Thinking is off by default; if you turn it on with "chat_template_kwargs": {"enable_thinking": true}, stream and cut off runaway output, since the card warns of thinking loops, and add --reasoning-parser qwen3 in vLLM or SGLang to split the reasoning out
  4. There's no generation_config.json, so pass the card's sampling yourself, for example temperature=1.0, top_p=1.0, top_k=20, presence_penalty=2.0 for text without thinking
  5. Use it for narrow steps or as a fine-tuning base, not as the main agent, as the card itself suggests
  6. Validate any JSON it returns, since structured output isn't documented

Questions

Which is better for AI agents, North Mini Code 1.0 or Qwen3.5-0.8B?

North Mini Code 1.0 scores 61 (C) on agent readiness against Qwen3.5-0.8B's 46.7 (D), and leads in 3 of 4 scored categories.

Other comparisons with North Mini Code 1.0 or Qwen3.5-0.8B

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report