FitMyLLM
INTEL· ALCHEMIST

Intel Arc A770 16GB

Running LLMs on the Arc A770 16GB — the long read: which models fit at which quantisation, and the settings worth changing. · Or what else $349 buys

VRAM
16 GB
MID-RANGE
BANDWIDTH
560
GB/S
MODELS Q4
262/449
58%
7B Q4 SPEED
~26
GOOD
▸ MODEL COVERAGE @ Q458% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
~60
TOK/S
7B
~26
TOK/S
14B
~13
TOK/S
32B
18.0GB NEEDED
70B
39.4GB NEEDED
▸ MEASURED RIG REPORTS

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

SEE THE REPORTS
▸ SPECIFICATIONS
VRAM
16 GB
BANDWIDTH
560 GB/s
FP16 COMPUTE
35 TFLOPS
TDP
225W
MEMORY
GDDR6
ARCHITECTURE
Alchemist
COMPUTE UNITS
32
PCIE
Gen 4 x16
MSRP
$349
117
FAST MODELS · >30 TOK/S
Real-time chat speed
260
USABLE · >10 TOK/S
Comfortable for all tasks
262
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ WHERE TO BUY

MSRP $349

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ DON’T WANT TO BUY?

Test Arc A770 16GB (or anything bigger) without committing. Pay by the second, cancel anytime.

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 262
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
1991
TOK/S · 3% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
1327
TOK/S · 4% VRAM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
1280
TOK/S · 4% VRAM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
1280
TOK/S · 4% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
700
TOK/S · 4% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
664
TOK/S · 4% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
588
TOK/S · 4% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
535
TOK/S · 4% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
535
TOK/S · 4% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
535
TOK/S · 4% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
512
TOK/S · 4% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
498
TOK/S · 4% VRAM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
472
TOK/S · 5% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
358
TOK/S · 5% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
358
TOK/S · 5% VRAM
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
345
TOK/S · 5% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
315
TOK/S · 5% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
315
TOK/S · 5% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
299
TOK/S · 5% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
299
TOK/S · 5% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
299
TOK/S · 5% VRAM
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
289
TOK/S · 5% VRAM
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
242
TOK/S · 6% VRAM
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
239
TOK/S · 6% VRAM
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
221
TOK/S · 6% VRAM
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
206
TOK/S · 6% VRAM
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
191
TOK/S · 7% VRAM
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
166
TOK/S · 7% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
163
TOK/S · 7% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
149
TOK/S · 8% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
149
TOK/S · 8% VRAM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
149
TOK/S · 8% VRAM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
149
TOK/S · 8% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
138
TOK/S · 8% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
138
TOK/S · 8% VRAM
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
138
TOK/S · 8% VRAM
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
133
TOK/S · 8% VRAM
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
126
TOK/S · 8% VRAM
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
126
TOK/S · 8% VRAM
S
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
119
TOK/S · 35% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Arc A770 16GB.

WHAT THIS CARD IS WORTH

Arc A770 16GB holds 262 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is ERNIE 4.5 21B A3B at IQ4_XS.

TOKENS/SEC PER $100
6.3
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
4.58 GB
what memory costs on this card
THE BIGGEST IT TAKES
ERNIE 4.5 21B A3B21.95B · IQ4_XS13.9 GB60 tok/sEST
GPT-OSS 20B21B · Q4_K_S13.8 GB48 tok/sEST
Reka Flash 321B · Q4_K_S14.2 GB8 tok/sEST
Reka Flash 3.121B · Q4_K_S14.2 GB8 tok/sEST
InternLM2 20B19.8B · Q4_K_M14.3 GB8 tok/sEST
InternLM2.5 20B19.8B · Q4_K_M14.3 GB8 tok/sEST
Ling-lite 16.8B16.8B · Q5_K_M13.6 GB59 tok/sEST
DeepSeek V2 Lite 16B16B · Q5_K_M12.9 GB59 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M1 Max (32GB)21 GB$1,4993.0 tok/s per $100
M2 Max (32GB)21 GB$1,7992.5 tok/s per $100
M2 Pro (32GB)21 GB$1,4991.9 tok/s per $100
M4 (32GB)21 GB$1,1991.7 tok/s per $100
Arc A770 16GB16 GB$3496.3 tok/s per $100

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

▸ DEVICE UNDER TEST

Intel Arc A770 16GB — 16 GB VRAM.

ARC A770 16GB SPEC
BRAND
Intel
VRAM
16 GB GDDR6
BANDWIDTH
560 GB/s
FP16 COMPUTE
35 TFLOPS
FP32 COMPUTE
17.2 TFLOPS
TDP
225 W
ARCHITECTURE
Alchemist
MSRP
$349
▸ AI CAPABILITY
262/ 449 models @ Q4

With 16 GB VRAM and 560 GB/s bandwidth, this GPU handles models up to 19.8B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~64 tok/s.

RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR ARC A770 16GB
262 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
InternLM2 20B19.8B12.6 GB945.1
InternLM2.5 20B19.8B12.6 GB950.9
Ling-lite 16.8B16.8B10.8 GB75
DeepSeek V2 Lite 16B16B10.3 GB7538.0
StarCoder2 15B15.96B10.2 GB1126.5
DeepSeek-Coder-V2-Lite 15.7B15.7B10.1 GB7543.0
DeepSeek-VL2 Small 16B15.7B10.1 GB7543.1
StarCoder 15B15.5B10.0 GB1221.0
InternVL3 14B15.12B9.7 GB1238.1
Phi-4-reasoning-vision 15B15B9.7 GB1242.8
DeepSeek R1 Distill Qwen 14B14.8B9.5 GB1243.9
DeepCoder 14B14.8B9.5 GB1238.7
Qwen2.5-Coder-14B14.8B9.5 GB1241.3
Qwen2.5-14B14.8B9.5 GB1241.3
Qwen3 14B14.8B9.5 GB1245.7
phi-4 14B14.66B9.4 GB1233.7
Phi-4-reasoning 14B14.66B9.4 GB1233.7
Phi-4-reasoning-plus 14B14.66B9.4 GB1275.5
Ministral 3 14B14B9.0 GB1325.9
Phi-3-medium-14b14B9.0 GB1333.7